Back to TUM-PREP Projects overview

Project Overview

Project Code: MGT 02

Project name:

Solving real-world routing problems using machine learning methods

TUM Department:

MGT – School of Management

TUM Chair / Institute:

Logistics and Supply Chain Management

Research area:

Solution methods for vehicle routing problems

Student background:

Computer Science/ InformaticsManagement / EconomicsMathematicsSustainability

Further disciplines:

Planned project location:

Arcisstraße 21
80333 Munich, Germany

Project Supervisor - Contact Details


Title:

Prof. Dr.

Given name:

Stefan

Family name:

Minner

E-mail:

stefan.minner@tum.de

Phone:

+49 (0)89 289 28201

Additional Project Supervisor - Contact Details


Title:

M.Sc.

Given name:

Christoph

Family name:

Kerscher

E-mail:

christoph.kerscher@tum.de

Phone:

+49 (0)89 289 28201

Additional Project Supervisor - Contact Details


Title:

Given name:

Family name:

E-mail:

Phone:

Project Description


Project description:

Background

Large companies and package delivery services must constantly face the problem of delivering several products from a depot or warehouse to a set of customers. To minimize transportation costs, such problems can be modeled as vehicle routing problems (VRPs). The solution will then tell the company which vehicle shall deliver which product to which customer. Adopting optimization and artificial intelligence (AI) techniques in modern logistics solutions has become widespread. Industrial companies integrate these methods into their applications to plan and optimize the transport business. The project will be part of a joint research project between TUM and SAP Labs Munich.

Motivation

The use of data-driven approaches and decomposition algorithms in the context of the VRP enables the solution of larger and more complex real-world problems. This touches on several more detailed questions to expand knowledge about artificial intelligence and advanced optimization. To achieve high user acceptance, the solutions must be simple, transparent, and robust to empower users to understand, trust, and effectively utilize AI technologies.

Research Project

Depending on the student’s background and interests, we will focus on one of the following topics:
- Developing and implementing new solution algorithms that combine elements of operations research and machine learning methods.
- Improving existing algorithms
- Developing a benchmark dataset for a real-world routing problem
- Benchmarking the advanced solution algorithms against well-known standard heuristics

Working hours per week planned:

32

Prerequisites


Required study level minimum (at time of TUM PREP project start):

2 years of bachelor studies completed

Subject related:

No specific subject requirements. But students should have an expertise on machine learning methods as described above.

Other:

  • Keine Stichwörter